US20200356073A1 - Prosthesis shape data generation system - Google Patents

Prosthesis shape data generation system Download PDF

Info

Publication number
US20200356073A1
US20200356073A1 US16/765,921 US201816765921A US2020356073A1 US 20200356073 A1 US20200356073 A1 US 20200356073A1 US 201816765921 A US201816765921 A US 201816765921A US 2020356073 A1 US2020356073 A1 US 2020356073A1
Authority
US
United States
Prior art keywords
shape data
prosthesis
stump
shape
dimensional
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
US16/765,921
Other languages
English (en)
Inventor
Yutaka TOKUSHIMA
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Instalimb Inc
Original Assignee
Instalimb Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Instalimb Inc filed Critical Instalimb Inc
Assigned to INSTALIMB, INC. reassignment INSTALIMB, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: Tokushima, Yutaka
Publication of US20200356073A1 publication Critical patent/US20200356073A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/78—Means for protecting prostheses or for attaching them to the body, e.g. bandages, harnesses, straps, or stockings for the limb stump
    • A61F2/80—Sockets, e.g. of suction type
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/4097—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by using design data to control NC machines, e.g. CAD/CAM
    • G05B19/4099—Surface or curve machining, making 3D objects, e.g. desktop manufacturing
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/5044—Designing or manufacturing processes
    • A61F2/5046—Designing or manufacturing processes for designing or making customized prostheses, e.g. using templates, finite-element analysis or CAD-CAM techniques
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/60—Artificial legs or feet or parts thereof
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/76—Means for assembling, fitting or testing prostheses, e.g. for measuring or balancing, e.g. alignment means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y30/00—Apparatus for additive manufacturing; Details thereof or accessories therefor
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y50/00—Data acquisition or data processing for additive manufacturing
    • B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y80/00—Products made by additive manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/5044—Designing or manufacturing processes
    • A61F2/5046—Designing or manufacturing processes for designing or making customized prostheses, e.g. using templates, finite-element analysis or CAD-CAM techniques
    • A61F2002/5047—Designing or manufacturing processes for designing or making customized prostheses, e.g. using templates, finite-element analysis or CAD-CAM techniques using mathematical models
    • A61F2002/5049—Computer aided shaping, e.g. rapid prototyping
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/5044—Designing or manufacturing processes
    • A61F2/5046—Designing or manufacturing processes for designing or making customized prostheses, e.g. using templates, finite-element analysis or CAD-CAM techniques
    • A61F2002/505—Designing or manufacturing processes for designing or making customized prostheses, e.g. using templates, finite-element analysis or CAD-CAM techniques using CAD-CAM techniques or NC-techniques
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/50—Prostheses not implantable in the body
    • A61F2/76—Means for assembling, fitting or testing prostheses, e.g. for measuring or balancing, e.g. alignment means
    • A61F2002/7615—Measuring means
    • A61F2002/762—Measuring means for measuring dimensions, e.g. a distance
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/35—Nc in input of data, input till input file format
    • G05B2219/35134—3-D cad-cam
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/49—Nc machine tool, till multiple
    • G05B2219/49023—3-D printing, layer of powder, add drops of binder in layer, new powder
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing

Definitions

  • the present invention relates to a prosthesis shape data generation system, a prosthesis shape data generation method, a prosthesis shape data generation program and a prosthesis generation system for generating shape data on a prosthesis, such as a prosthetic arm or hand, a prosthetic finger or a prosthetic leg or foot, for example.
  • a prosthesis In order to restore the shape or function of a missing body part, a prosthesis can be attached to the stump of the missing body part.
  • producing such conventional prostheses imposes time, economic or other burdens.
  • prostheses are customized by orthotists and therefore are expensive.
  • prostheses need to be renewed once in several years as the body grows or the prothesis wears, and the economic burdens is heavy.
  • finishing a prosthesis requires a plurality of visits to a hospital and various manual processes by experts, such as plaster casting and adjustment, and the users generally have to wait for one month or longer.
  • Patent Literature 1 discloses a system that facilitates duplication and modification of a prosthesis by centrally managing, on the Internet, data such as attribute information on a user and three-dimensional data on a prosthesis socket produced in the past.
  • Patent Literature 1 Japanese Utility Model Registration No. 3089376
  • Patent Literature 1 only builds a database of past information on a prosthesis of an individual, and no mention is made of a specific method of designing a prosthesis shape that fits a stump or a method of reducing the time and economic burdens involved with the fitting operation by an orthotist or the like. Therefore, a properly fitted prosthesis cannot be quickly and economically manufactured.
  • the present invention has been devised in view of the above technical background, and an object of the present invention is to quickly and economically manufacture a prosthesis that fits the shape of a stump of a prosthesis user.
  • the technical problem described above can be solved by a prosthesis shape data generation system, a prosthesis shape data generation method, a prosthesis shape data generation program and a prosthesis shape data generation network system configured as described below.
  • a prosthesis shape data generation system includes: a stump shape data acquisition unit that acquires stump shape data, which is shape data on a stump of a living body; and an estimated prosthesis shape data generation unit that performs an estimation processing by inputting the stump shape data to a machine learning model that has previously learnt a correspondence between a stump shape and a shape of a part or a whole of a prosthesis that fits the stump shape, thereby generating estimated prosthesis shape data that is shape data on a part or a whole of a prosthesis that fits the stump of the living body.
  • shape data on a part (such as a socket part) or the whole of a prosthesis that fits a stump can be generated based on shape data on the stump by using the machine learning technique. Therefore, a prosthesis or a part thereof (such as a socket part thereof) that fits a stump can be generated without a high degree of expertise in orthotics, and the time and economic burdens are reduced.
  • the living body described above may be the body of a human being or an animal, for example.
  • the prosthesis data generation system may further include a modified prosthesis shape data generation unit that permits a modification to the estimated prosthesis shape data generated by the estimated prosthesis shape data generation unit and, if the modification is performed, generates modified prosthesis shape data that is prosthesis shape data resulting from the modification.
  • the modification described above includes not only a quantitative modification to digital data but also prototyping using a three-dimensional printer device and a three-dimensional scanner device and a physical modification to the prototype.
  • the prosthesis data generation system may further include: a final shape determination unit that determines the modified prosthesis shape data generated by the modified prosthesis shape data generation unit to be final prosthesis shape data on the part or the whole of the prosthesis that fits the stump of the living body; and a machine learning processing unit that performs a learning process on the machine learning model based on the stump shape data and the final prosthesis shape data to improve an estimation precision of the machine learning model.
  • a final shape determination unit that determines the modified prosthesis shape data generated by the modified prosthesis shape data generation unit to be final prosthesis shape data on the part or the whole of the prosthesis that fits the stump of the living body
  • a machine learning processing unit that performs a learning process on the machine learning model based on the stump shape data and the final prosthesis shape data to improve an estimation precision of the machine learning model.
  • the machine learning is performed based on the final, modified or otherwise refined prosthesis shape data, the estimation precision of the machine learning model can be further improved as the number of samples increases.
  • the prosthesis shape data generation system may further include: a three-dimensional printer unit that performs three-dimensional printing corresponding to three-dimensional prosthesis shape data based on arbitrary three-dimensional prosthesis shape data; and a three-dimensional scanner unit that scans an arbitrary three-dimensional shape to generate three-dimensional shape data corresponding to the three-dimensional shape, and the modification performed in the modified prosthesis shape data generation unit may be performed by scanning a three-dimensional shape obtained by physically modifying a three-dimensional printed body generated by the three-dimensional printer unit.
  • the prosthesis shape data generation system may further include an additional information acquisition unit that acquires additional information on the living body, and the estimated prosthesis shape data generation unit may further perform an estimation processing by using the stump shape data and the additional information as an input to the machine learning model that has previously learnt a correspondence between a stump shape and additional information and a shape of a part or a whole of a prosthesis that fits the stump shape, thereby generating estimated prosthesis shape data that is shape data on a part or a whole of a prosthesis that fits the stump of the living body.
  • the prosthesis shape data generation system may further include a three-dimensional shape editing unit that receives arbitrary prosthesis shape data and edits the prosthesis shape data by three-dimensional CAD, and the modification performed in the modified prosthesis shape data generation unit may be performed by the three-dimensional CAD in the three-dimensional shape editing unit.
  • the prosthesis shape data can be edited using three-dimensional CAD, a quantitative modification can be made.
  • further learning can be performed based on the modified shape data, the estimation precision of the machine learning model can be appropriately improved.
  • the present invention can also be embodied as a prosthesis shape data generation network system.
  • the prosthesis production system includes a local network; and a server connected to the local network via an internet, the local network includes: a three-dimensional scanner unit that scans an arbitrary three-dimensional shape to generate corresponding three-dimensional shape data; and a stump shape data acquisition unit that acquires stump shape data, which is shape data on a stump of a living body generated by the three-dimensional scanner unit, the server includes an estimated prosthesis shape data generation unit that performs an estimation processing by inputting the stump shape data to a machine learning model that has previously learnt a correspondence between a stump shape and a shape of a part or a whole of a prosthesis that fits the stump shape, thereby generating estimated prosthesis shape data that is shape data on a part or a whole of a prosthesis that fits the stump of the living body, the stump shape data acquired by the stump shape data acquisition unit is transmitted to the server via the internet, and the estimated prosthesis shape data generation unit generates the
  • shape data on a part of a prosthesis (such as a socket part of a prosthesis) or the whole of a prosthesis that fits a stump can be generated based on the shape data on the stump by using the machine learning technology.
  • a prosthesis or a part thereof (such as a socket) that fits a stump can be produced without a high degree of expertise in orthotics, and the time and economic burdens can be reduced.
  • the machine learning or the like does not have to be performed on the local network, and the computation load can be distributed.
  • the stump shape data or the like obtained in each local network can be centralized in the server. As a result, the machine learning can be performed based on various patterns, and the estimation precision can be further improved.
  • a prosthesis shape data generation method includes: a stump shape data acquisition step of acquiring stump shape data, which is shape data on a stump of a living body; and an estimated prosthesis shape data generation step of performing an estimation processing by inputting the stump shape data to a machine learning model that has previously learnt a correspondence between a stump shape and a shape of a part or a whole of a prosthesis that fits the stump shape, thereby generating estimated prosthesis shape data that is shape data on a part or a whole of a prosthesis that fits the stump of the living body.
  • a prosthesis shape data generation program is a prosthesis shape data generation program that makes a computer perform: a stump shape data acquisition step of acquiring stump shape data, which is shape data on a stump of a living body; and an estimated prosthesis shape data generation step of performing an estimation processing by inputting the stump shape data to a machine learning model that has previously learnt a correspondence between a stump shape and a shape of a part or a whole of a prosthesis that fits the stump shape, thereby generating estimated prosthesis shape data that is shape data on a part or a whole of a prosthesis that fits the stump of the living body.
  • shape data on a part of a prosthesis (such as a socket part of a prosthesis) or the whole of a prosthesis that fits a stump can be generated based on shape data on the stump by using a machine learning technology. Therefore, a prosthesis or a part thereof (such as a socket) that fits a stump can be produced without a high degree of expertise in orthotics, and the time and economic burdens can be reduced.
  • FIG. 1 is a conceptual diagram showing the whole of a network system.
  • FIG. 2 is a (first) diagram for illustrating an example of an operation of the network system.
  • FIG. 3 is a (second) diagram for illustrating the example of the operation of the network system.
  • FIG. 4 is a detailed flowchart showing a modification process.
  • FIG. 5 is a conceptual diagram showing a learning process using a neural network.
  • FIG. 6 is a diagram for illustrating an overview of the system.
  • the prosthesis shape data generation system 100 includes a local network 10 and a server system 50 , the local network 10 is formed by an interconnection of an information processing device 11 that includes a CPU or GPU for performing various controls, a memory and an input/output device, such as a keyboard or a display, and performs various information processings described later, a three-dimensional scanner device 12 (such as a 3D scanner) that scans an arbitrary three-dimensional shape to generate three-dimensional shape data, and a three-dimensional printer device 13 (such as a 3D printer) that prints a three-dimensional shape based on arbitrary three-dimensional shape data, and the server system 50 is connected to the local network 10 via the Internet 30 and is formed by a storage device 51 that stores various kinds of information described later and a server device 52 that includes a control unit, a storage unit and the like and performs a machine learning process or the like described later.
  • an information processing device 11 that includes a CPU or GPU for performing various controls
  • a memory and an input/output device such as a
  • the server system 50 is in a so-called cloud environment, and the server device 52 may perform distributed processing or processing under virtualization in a predetermined manner, for example.
  • the storage device 51 does not have to be located at one location and may be distributed or configured as a predetermined storage system, for example.
  • FIGS. 2 and 3 shows an example of an operation of the prosthesis shape data generation system 100 .
  • the left halves of the drawings show processings performed in the local network 10
  • the right halves of the drawings show processings performed in the server system 50 .
  • the information processing device 11 when a process is started, the information processing device 11 performs a processing of acquiring three-dimensional stump scan data generated by the three-dimensional scanner device 12 scanning a stump of a human body (S 100 ), and transmits the acquired stump scan data to the server system 50 via the internet 30 (S 101 ). After the transmission, the information processing device 11 waits until the information processing device 11 receives an estimation computation result described later (as far as No in S 102 ).
  • the server device 52 After the process is started, when the server device 52 that is waiting until the server device 52 receives the stump scan data (as far as NO in S 200 ) receives the stump scan data from the information processing device 11 (if YES in S 200 ), the server device 52 saves the received stump scan data in the storage unit of the server device 52 or the storage device 51 (S 201 ). The server device 52 then inputs the stump scan data to a learning model, which has previously leant the correspondence between s stump shape and the shape of a part of a prosthesis that fits the stump shape, the shape of a prosthesis socket in this embodiment, to perform an estimation computation processing for estimating prosthesis socket shape data that fits the stump shape (S 202 ).
  • the result of the estimation computation processing that is, the prosthesis socket shape data that fits the stump, is transmitted to the information processing device 11 (S 203 ) and the prosthesis socket shape data corresponding to the estimation computation result is saved in the storage unit of the server device 52 or the storage device 51 .
  • the learning model can be any of various types of learning models.
  • an artificial neural network is used as the learning model.
  • FIG. 4 shows a flow of the prototyping process in detail.
  • a mode selection processing occurs in which a user is prompted to perform mode selection via a GUI or the like on the display (S 1031 ).
  • a “CAD modification mode” in which the prosthesis socket shape data corresponding to the estimation computation result (or the latest or selected prosthesis socket shape data in the case where the prototyping process or the like has previously been performed) is modified using three-dimensional CAD
  • a “provisional output mode” in which the three-dimensional printer device 13 provisionally outputs the estimation computation result (or the latest or selected prosthesis socket shape data in the case where the prototyping process or the like has previously been performed
  • a “3D scan mode” in which the three-dimensional scanner device 12 scans a predetermined prosthesis socket or the provisionally output prosthesis socket again.
  • the three-dimensional printer device 13 may perform the printing in a simplified mode in which output is completed in about several (two to three) hours, since the output is provisional output.
  • the estimation computation result (or the latest or selected prosthesis socket shape data in the case where the prototyping process or the like has previously been performed) is read (S 1032 ).
  • a processing is then performed to permit or prompt editing of the read prosthesis socket shape data using three-dimensional CAD (S 1033 ).
  • the edited data is stored in the storage unit of the information processing device 11 (S 1034 ). That is, in the “CAD modification mode”, the prosthesis shape can be quantitatively modified on the information processing device 11 .
  • the estimation computation result (or the latest or selected prosthesis socket shape data in the case where the prototyping process or the like has previously been performed) is read (S 1036 ).
  • a processing is then performed in which the three-dimensional printer device 13 three-dimensionally outputs the read prosthesis socket shape data (S 1037 ).
  • the three-dimensional printer device 13 may perform the printing in a simplified mode in which output is completed in about several (two to three) hours, since the output is provisional output.
  • a processing is performed in which three-dimensional scanning of a predetermined prosthesis socket or a prosthesis socket that is a provisionally output printed body is performed (S 1039 ).
  • the shape data obtained by the three-dimensional scanning is stored in the storage unit of the information processing device 11 (S 1040 ).
  • the prosthesis socket shape that is a three-dimensional printed body provisionally output (prototyped) by the “provisional output mode” can be physically modified (trimmed, for example), and then the modified prosthesis socket shape can be converted into three-dimensional shape data again by the “3D scan mode”. Therefore, an intuitive modification based on the accumulated experience or expertise of an expert, such as an orthotist, can also be made.
  • the three modes described above that is, the “CAD modification mode”, the “provisional output mode” and the “3D scan mode” are performed until the prosthesis socket shape fits, or is determined to fit, the stump (until NO in S 1042 ).
  • the series of processings is completed (if YES in S 1042 )
  • the prototyping process ends, and the resulting prosthesis socket shape is designated as final prosthesis socket shape data.
  • the modified prosthesis socket shape data after the prototyping process is transmitted from the information processing device 11 to the server device 52 (S 104 ).
  • a signal indicating that no modification has been made is transmitted from the information processing device 11 to the server device 52 .
  • a processing is performed to allow the three-dimensional printer device 13 to perform full output (S 105 ). As the full output, the three-dimensional printer device 13 may perform precise three-dimensional printing over more than ten hours (such as 12 to 24 hours), for example.
  • the server device 52 if the server device 52 that is waiting until the server device 52 receives the modified prosthesis socket shape data (as far as NO in S 204 ) receives the modified prosthesis shape data from the information processing device 11 (if YES in S 204 ), the server device 52 first saves the modified prosthesis shape data in the storage unit therein or the storage device 51 (S 205 ). The server device 52 then reads the estimation computation result saved (in S 203 ) and the modified prosthesis socket shape data, and performs a machine learning process for learning the correspondence therebetween (S 206 ). When the machine learning process is completed, a learnt parameter (weight or the like) is saved in the storage unit of the server device 52 or the storage device 51 (S 207 ), and the process ends.
  • a learnt parameter weight or the like
  • the server device 52 receives the signal indicating that no modification has been made, rather than the modified prosthesis socket shape data, from the information processing device 11 (if YES in S 204 ), the process ends without performing the processing of saving the modified data (S 205 ) and the machine learning process (S 206 and S 207 ). This is because it is determined that the precision of the estimation processing is sufficient, and further machine learning is not needed.
  • the machine learning is not performed if the server device 52 receives the signal indicating that no modification has been made in this embodiment, the machine learning can also be performed using the data that does not need to be modified, in order to reinforce the parameter used when outputting the data of high estimation precision.
  • FIG. 5 is a conceptual diagram showing an example of the machine learning process, in particular, the machine learning process performed using an artificial neural network.
  • the artificial neural network used in this embodiment is a multi-layer artificial neural network having an input layer, a plurality of intermediate layers and an output layer, and is formed by nodes, which correspond to neurons, and weighted links (weights), which correspond to synapses responsible for transmission between neurons and connect nodes to each other, as shown in the middle part of the drawing.
  • weights weighted links
  • the machine learning process includes a forward computation processing and an error back propagation computation processing.
  • the forward computation processing will be described.
  • the three-dimensional shape data on the stump or data corresponding thereto is input to the input layer shown in the left part of the drawing.
  • the stump is a below-knee stump.
  • the firing values of the neurons are computed based on the weights between the nodes, and a forward propagation occurs from left to right in the drawing.
  • a transfer function for each neuron a ramp function (ReLU) or a sigmoid function can be used, for example.
  • the estimation machine outputs the three-dimensional shape data on the part (socket) of the prosthesis from the three-dimensional shape data on the stump or data corresponding thereto.
  • the forward computation is first performed, and then, a processing is performed in which an error is calculated between the three-dimensional shape data on the prosthesis socket corresponding to the estimation computation result and the modified prosthesis socket shape data corresponding to teaching data received from the information processing device 11 .
  • the error calculated in this processing propagates to the input layer according to the error back propagation algorithm, and the parameter such as the numeric value corresponding to the weight is updated or modified based on the back-propagated error.
  • the learning model performs such a series of processings on many various pairs of input data and teaching data, thereby learning the expertise of the orthotist or other person who has modified the shape data. As a result, the estimation precision of the learning model is gradually improved.
  • a part of a prosthesis (such as a socket part of a prosthesis) that fits a stump can be produced based on the shape data on the stump by using the machine learning technology.
  • a prosthesis or a part thereof (such as a socket) that fits a stump can be produced without a high degree of expertise in orthotics, and the time and economic burdens can be reduced.
  • the estimation precision of the machine learning model can be further improved as the number of samples increases.
  • FIG. 6 is a diagram for illustrating an overview of the prosthesis socket shape data generation system 100 described above. With reference to the drawing, an example of a process will be described in which a prosthesis provider uses the prosthesis shape data generation system 100 to provide a prosthesis to a prosthesis user.
  • the prosthesis provider first interviews the prosthesis user, and then uses the three-dimensional scanner device 12 to scan the three-dimensional shape of the stump of the prosthesis user. After the scanning, the prosthesis provider transmits the three-dimensional shape data on the scanned stump to the server device 52 (S 100 , S 101 ).
  • the three-dimensional shape data on the scanned stump is uploaded to the server device 52 in the cloud environment and input to the estimation machine (learning model), and the estimation machine (learning model) estimates and computes the three-dimensional data on the prosthesis socket (S 200 to S 202 ).
  • the estimation computation result that is, the three-dimensional shape data on the prosthesis socket, is transmitted and recommended to the information processing device 11 of the prosthesis provider (S 203 ).
  • the estimation computation result that is, the three-dimensional shape data on the prosthesis socket
  • the modifications include both digital or quantitative modifications using three-dimensional CAD (S 1032 to S 1034 ) and analog modifications including provisional output by the three-dimensional printer device 13 (S 1036 to S 1037 ), a physical modification (such as trimming) to the provisionally output printed body and the subsequent scanning of the modified printed body (S 1039 to S 1040 ).
  • the modified three-dimensional prosthesis shape data on the prosthesis socket is transmitted and imported to the server device 52 (S 104 , S 204 to S 205 ).
  • the modified three-dimensional shape data on the prosthesis socket is fully output by the three-dimensional printer device 13 (S 105 ), other components are assembled to the output prosthesis, and the finished prosthesis is provided to the prosthesis user.
  • the learning model on the server device 52 that is, the artificial neural network, performs a learning process using the shape of the stump of the prosthesis as an input and the modified three-dimensional shape data on the prosthesis socket as teaching data (S 206 to S 207 ). In this way, the estimation precision of the learning model can be further improved.
  • the machine learning is performed using the stump shape of the prosthesis as an input and the modified three-dimensional prosthesis shape data on the prosthesis socket as teaching data.
  • the present disclosure is not limited to the implementation.
  • the whole of the prosthesis may be output, rather than a part of the prosthesis, such as the prosthesis socket.
  • additional information on the properties of the prosthesis user such as age, sex, weight, muscle mass, body fat mass, soft tissue mass, position of the bone of the stump, or pigeon-toed/bow-legged or anteversion/retroversion in the case of a prosthetic leg or foot, may be obtained in the interview, input to the information processing device 11 and transmitted to the server device 52 , and the learning process may be performed by using the additional information and the shape of the stump as inputs and the modified three-dimensional shape data on the prosthesis socket as teaching data.
  • shape data on a part or the whole of the prosthesis that more precisely fits the stump can be generated.
  • a simple artificial neural network is used.
  • the present disclosure is not limited to the implementation.
  • Various other machine learning algorithms that gradually acquire a generalization capability such as a support vector machine (SVM)
  • SVM support vector machine
  • Even when the artificial neural network is used a fully connected neural network may be used, or a convolutional neural network (CNN) or the like may be arranged before or after the artificial neural network, for example.
  • CNN convolutional neural network
  • the learning process instead of sequentially performing the learning process for each data set, the learning process may be performed for each batch of a plurality of patterns accumulated.
  • a structure having an increased number of intermediate layers may be used to perform deep learning.
  • the stump shape data or the prosthesis shape data itself is transmitted as three-dimensional data between the information processing device 11 and the server device 52 .
  • the present disclosure is not limited to the implementation.
  • an appropriate information compression or data structure conversion may be performed for transmission, in order to reduce the amount of information.
  • the transmission may be performed after the data is converted into a format suitable for machine learning.
  • the devices are divided into those in the local network 10 and those in the server system 50 .
  • the network configuration is not limited to such a configuration but can be modified.
  • all the processes according to the present invention including the machine learning process may be performed in the local network 10 , or the three-dimensional scanner device 12 and the three-dimensional printer device 13 may be located in different networks.
  • all the processes according to the present disclosure including the machine learning process may be performed in one information processing device 11 .
  • the present disclosure can be used at least in the prosthesis manufacturing industry and associated industries.
US16/765,921 2017-11-21 2018-11-20 Prosthesis shape data generation system Pending US20200356073A1 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
JP2017-223984 2017-11-21
JP2017223984 2017-11-21
PCT/JP2018/042889 WO2019103010A1 (ja) 2017-11-21 2018-11-20 義肢形状データ生成システム

Publications (1)

Publication Number Publication Date
US20200356073A1 true US20200356073A1 (en) 2020-11-12

Family

ID=66632007

Family Applications (1)

Application Number Title Priority Date Filing Date
US16/765,921 Pending US20200356073A1 (en) 2017-11-21 2018-11-20 Prosthesis shape data generation system

Country Status (5)

Country Link
US (1) US20200356073A1 (ja)
EP (1) EP3714844A4 (ja)
JP (2) JP6948726B2 (ja)
PH (1) PH12020550619A1 (ja)
WO (1) WO2019103010A1 (ja)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11559925B2 (en) 2016-12-19 2023-01-24 Lantos Technologies, Inc. Patterned inflatable membrane

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102020107623A1 (de) * 2020-03-19 2021-09-23 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Computerimplementiertes verfahren zum erstellen von steuerungsdatensätzen, cad-cam-system und fertigungsanlage

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2578061B2 (ja) * 1993-07-19 1997-02-05 株式会社エイ・ティ・アール人間情報通信研究所 義肢制御装置
JP2000090272A (ja) * 1998-09-16 2000-03-31 Hitachi Zosen Corp 靴の選定方法
JP3089376U (ja) * 2002-02-26 2002-10-25 善博 三好 義肢製作装置
JP2003299679A (ja) * 2002-04-11 2003-10-21 Yamanashi Prefecture 義肢ソケット製造システムと義肢ソケットの製造方法
JP4304341B2 (ja) * 2005-03-17 2009-07-29 国立大学法人 新潟大学 ３次元形状の計測装置およびその計測データによる義肢のソケット形状設計装置
US20070233267A1 (en) * 2006-03-29 2007-10-04 Farid Amirouche Application of neural networks to prosthesis fitting and balancing in joints
US8366789B2 (en) * 2008-05-28 2013-02-05 3D Systems, Inc. Prosthetic limb
US8423167B2 (en) * 2008-07-24 2013-04-16 University Of Washington Computer aided design and manufacturing of transtibial prosthetic sockets
WO2013058978A1 (en) * 2011-10-17 2013-04-25 Kimmel Zebadiah M Method and apparatus for sizing and fitting an individual for apparel, accessories, or prosthetics
JP2016077853A (ja) * 2014-10-17 2016-05-16 明伸興産株式会社 義肢および義肢作成方法
WO2017123729A1 (en) * 2016-01-13 2017-07-20 Massachusetts Institute Of Technology Method and system for designing a biomechanical interface contacting a biological body segment
US10905568B2 (en) * 2016-02-29 2021-02-02 Pva Medical, Llc Prosthetic limb socket with variable hardness
US20180235779A1 (en) * 2017-02-17 2018-08-23 Ralph Wayne Dudding Two-part prosthetic socket and method of making same

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11559925B2 (en) 2016-12-19 2023-01-24 Lantos Technologies, Inc. Patterned inflatable membrane
US11584046B2 (en) 2016-12-19 2023-02-21 Lantos Technologies, Inc. Patterned inflatable membranes

Also Published As

Publication number Publication date
JP6948726B2 (ja) 2021-10-13
JPWO2019103010A1 (ja) 2020-12-24
PH12020550619A1 (en) 2021-03-01
JP7264524B2 (ja) 2023-04-25
EP3714844A1 (en) 2020-09-30
JP2022023032A (ja) 2022-02-07
EP3714844A4 (en) 2021-08-18
WO2019103010A1 (ja) 2019-05-31

Similar Documents

Publication Publication Date Title
JP7264524B2 (ja) 義肢形状データ生成システム、方法、プログラム及び義肢生成システム
US20170246013A1 (en) Prosthetic limb socket with variable harness
Steer et al. Predictive prosthetic socket design: part 2—generating person-specific candidate designs using multi-objective genetic algorithms
Comotti et al. Multi-material design and 3D printing method of lower limb prosthetic sockets
Cabibihan et al. A method for 3-d printing patient-specific prosthetic arms with high accuracy shape and size
US20110161058A1 (en) Method, system, apparatus and computer program for creating a prosthesis socket
CN105956349A (zh) 一种基于有限元力学分析的鞋垫制作系统
US20230148865A1 (en) Apparatus for anatomic three dimensional scanning and automated three dimensional cast and splint design
US20240120094A1 (en) Theory-motivated domain control for ophthalmological machine-learning-based prediction method
US11741277B2 (en) Predictive modeling platform for serial casting to correct orthopedic deformities
Górski et al. Automated design of customized 3D-printed wrist orthoses on the basis of 3D scanning
CN112862072A (zh) 基于云平台及大数据的义齿自动匹配生产方法及系统
Colombo et al. A full virtual approach to design and test lower limb prosthesis: This paper reports a software platform for design and validation of lower limb prosthesis in a completely virtual environment, potentially replacing current manual process
Iglesias et al. Immunological approach for full NURBS reconstruction of outline curves from noisy data points in medical imaging
Nayak et al. Topology optimisation of transtibial prosthesis socket using finite element analysis
US20200138522A1 (en) 3d model generation using thermal imaging and x-ray
Müller et al. Reasoning Mechanism for the Implementation of Computational Design Synthesis
Colombo et al. Socket modelling assistant for prosthesis design
CN116264995A (zh) 脊柱侧弯矫形支具的个性化3d建模方法、计算机设备
US20170285618A1 (en) Systems and methods for integrated robust orthotics and prosthetics hyper-customization
CN113345558A (zh) 一种提高骨科诊断决策效率的辅助系统及方法
WO2021087483A1 (en) Predictive modeling platform for serial casting to correct orthopedic deformities
Kidder et al. 3D model acquisition, design, planning, and manufacturing of orthopaedic devices: a framework
US20230355362A1 (en) Automatic creation of a virtual model of at least a part of an orthodontic appliance
Zwettler et al. Towards an Automated Process for Adaptive Modelling of Orthoses and Shoe Insoles in Additive Manufacturing

Legal Events

Date Code Title Description
AS Assignment

Owner name: INSTALIMB, INC., JAPAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:TOKUSHIMA, YUTAKA;REEL/FRAME:052721/0512

Effective date: 20200517

STPP Information on status: patent application and granting procedure in general

Free format text: APPLICATION DISPATCHED FROM PREEXAM, NOT YET DOCKETED

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STPP Information on status: patent application and granting procedure in general

Free format text: NON FINAL ACTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE TO NON-FINAL OFFICE ACTION ENTERED AND FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: FINAL REJECTION MAILED

STPP Information on status: patent application and granting procedure in general

Free format text: RESPONSE AFTER FINAL ACTION FORWARDED TO EXAMINER

STPP Information on status: patent application and granting procedure in general

Free format text: ADVISORY ACTION MAILED

STCV Information on status: appeal procedure

Free format text: NOTICE OF APPEAL FILED

STCV Information on status: appeal procedure

Free format text: APPEAL BRIEF (OR SUPPLEMENTAL BRIEF) ENTERED AND FORWARDED TO EXAMINER

STCV Information on status: appeal procedure

Free format text: ON APPEAL -- AWAITING DECISION BY THE BOARD OF APPEALS